Nicolas Patry 799a193b10 Fixing Phi3.		2024-06-01 08:47:00 +00:00
..
__init__.py	…
bloom_modeling.py	…
clip.py	…
flash_cohere_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_dbrx_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_gemma_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_gpt2_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_llama_modeling.py	Fixing Phi3.	2024-06-01 08:47:00 +00:00
flash_mistral_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_mixtral_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_neox_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_pali_gemma_modeling.py	Pali gemma modeling (#1895)	2024-05-16 06:58:47 +02:00
flash_phi_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_qwen2_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_rw_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_santacoder_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
flash_starcoder2_modeling.py	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
idefics2.py	MLPSpeculator. (#1865)	2024-05-14 12:33:18 +02:00
idefics_config.py	…
idefics_image_processing.py	…
idefics_modeling.py	reenable xpu for tgi (#1939)	2024-05-23 14:11:08 +02:00
idefics_perceiver.py	…
idefics_processing.py	…
idefics_vision.py	…
llava_next.py	MLPSpeculator. (#1865)	2024-05-14 12:33:18 +02:00
mamba_modeling.py	…
mpt_modeling.py	…
neox_modeling.py	…
opt_modeling.py	…
phi_modeling.py	…
siglip.py	Removing some unused code. (#1915)	2024-05-17 11:35:49 +02:00
t5_modeling.py	…
vlm.py	Pali gemma modeling (#1895)	2024-05-16 06:58:47 +02:00